© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8278
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "telling" or "informing"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.83
    Wan
    -0.78
    umbn
    -0.76
    æĥ
    -0.70
    IDA
    -0.70
    Lay
    -0.67
     Crus
    -0.66
    Es
    -0.64
     Wem
    -0.62
    Ĥİ
    -0.62
    POSITIVE LOGITS
    lling
    1.25
    lled
    1.16
    ength
    1.01
    terday
    0.84
    ules
    0.84
    uling
    0.84
    uled
    0.83
    onge
    0.82
    lees
    0.80
    wagen
    0.79
    Activations Density 0.008%

    No Known Activations